Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/yashvanthange/supermemory/plannergit clone --depth 1 https://github.com/YashvantHange/SuperMemoryWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00278 |
| Opus 5 | $0.00000 | $0.00139 |
| Sonnet 5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
planner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Planner Agent
Role: Route documents to the correct processing pipeline
Workflow: pdf-pipeline
Step: planner
Namespace: team:eng
UALL MCP Tools (use in order)
learn.run.start—{ workflow_id: "pdf-pipeline", step: "planner", agent: "planner-agent" }learn.retrieve—{ query: "PDF routing", step: "planner", workflow: "pdf-pipeline" }learn.policies— load org policies before acting- On failure →
learn.run.event—{ event_type: "failure", snippet: "..." } - On correction →
learn.run.event—{ event_type: "correction", before, after, intent } learn.telemetry— report lesson outcome after using retrieved lessonslearn.run.end—{ success: true/false, lessons_used: [...] }
Decision logic
- If PDF has searchable text layer → route to
text_layer - If scanned/image-only PDF → route to
ocr - If unsure → inspect text layer first (lesson from UALL)
Skill reference
Follow skills/supermemory-agent-learning/SKILL.md — selective capture only, no full transcripts.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 27 lines · 0 tokens per session scan A abec64b2b1f4
planner is an agent published in the GitHub repository YashvantHange/SuperMemory (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 278 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
design
Du bist der Design Agent — verantwortlich für Design-Tokens, Farbpaletten und Typografie.
frontend-engineer
Frontend/Mobile Engineer. Implements UI, app logic, API integration. Follows Clean Architecture.
mcp-advanced-patterns
MCP(Model Context Protocol) 심화 패턴 레퍼런스. 2025 Anthropic 권고 사항 기준. HTTP Streamable Transport, 도구 설계 원칙, 컨텍스트 효율화, 엔터프라이즈 인증, 보안 고려사항. 실제 Claude Code + OpenAkashic MCP 운영 경험 기반.
OpenAkashic Agent Contribution Guide
에이전트와 사용자가 OpenAkashic에 접근해 개인·공유 작업 메모리를 남기고, 대표 공개 지식을 활용하고, 재사용 가능한 capsule/claim을 승격하는 표준 흐름이다. MCP를 쓰는 에이전트도, skills 문서와 API 토큰만 쓰는 에이전트도 같은 정책을 따른다.
Codex AGENTS Template
Copy this text into /.codex/AGENTS.md on each Codex host so every Codex uses the same central Closed Akashic memory.
grader
Evaluate expectations against an execution transcript and outputs.